© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1050
    Prev
    Next
    INDEX
    Explanations

    phrases related to manual labor or physical activities with hands

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to the concept of "hand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iatus
    -0.66
    ioxide
    -0.65
    QL
    -0.65
     reservations
    -0.62
     Belle
    -0.62
     constitu
    -0.58
     Atmosp
    -0.58
     exclus
    -0.57
     Revenue
    -0.57
    istor
    -0.57
    POSITIVE LOGITS
    picked
    1.00
    held
    0.96
    forward
    0.93
    washing
    0.90
     wielded
    0.90
    eye
    0.88
    mint
    0.87
    painted
    0.85
    forth
    0.84
    crafted
    0.84
    Activations Density 0.094%

    No Known Activations